Predictive Classifier for Cardiovascular Disease Based on Stacking Model Fusion

Abstract

The etiology of cardiovascular disease is still an unsolved world problem, and high morbidity, disability, and mortality are the main characteristics of cardiovascular diseases. There is, therefore, a need for effective and rapid early prediction of likely outcomes in patients with cardiovascular disease using artificial intelligence (AI) techniques. The Internet of Things (IoT) is becoming a catalyst for enhancing the capabilities of AI applications. Data are collected through IoT sensors and analyzed and predicted using machine learning (ML). Existing traditional ML models do not handle data inequities well and have relatively low model prediction accuracy. To address this problem, considering the data observation mechanism and training methods of different algorithms, this paper proposes an ensemble framework based on stacking model fusion, from Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest (RF), Extra Tree (ET), Gradient Boosting Decision Tree (GBDT), XGBoost, LightGBM, CatBoost, and Multilayer Perceptron (MLP) (10 classifiers to select the optimal base learners). In order to avoid the overfitting phenomenon generated by the base learners, we use the Logistic Regression (LR) simple linear classifier as the meta learner. We validated the proposed algorithm using a fused Heart Dataset from several UCI machine learning repositories and another publicly available Heart Attack Dataset, and compared it with 10 single classifier models. The experimental results show that the proposed stacking classifier outperforms other classifiers in terms of accuracy and applicability.

Heart disease risk prediction using deep learning techniques with feature augmentation

“…An stacking technique formed by K-NN and Logistic Regresion followed by a k-NN classification using the vote classifier output of the previous techniques obtained the best results with a 87.24% of accuracy. In 2022, Ghosh et al [13] achieved an accuracy of 86.40% when using Random Forest Model Lately, in [21] an stacking algorithm was proposed which combines the output of Logistic Regression, Random Forest, MLP, Cat Boost and Decision Trees and trains a meta classifier to derive the final result. This method achieved an accuracy of 89.86% over the same experimental conditions than our proposal.…”

A WOA-Stacking Tobacco Leaf Grading Method Based on Multi-Heterogeneous Classifiers Ensemble

“…Nowadays, the use of appropriate technology to replace the traditional artificial tobacco leaf grading has become one of the technical difficulties that the tobacco industry needs to urgently solve [7]. In the field of tobacco grading research, to achieve double-sided imaging grading of tobacco without human operation, the combination of Convolutional Neural Networks (CNN) classifier and dual-branch integration can establish a classification model for the front and back of tobacco [8]. Support vector machines (SVM) are also commonly used in tobacco grading.…”

Enhancing Heart Disease Prediction Accuracy through Machine Learning Techniques and Optimization

“…Using search constraints, a rule-generation algorithm has been used for the early detection of heart attacks [3]. Moreover, recent advances in healthcare technology have driven the development of machine learning (ML) systems for the prediction of human health diseases [4][5][6]. There have been many researchers working on the development of improved ML models.…”